Papers › LLMs generate structurally realistic social networks but overestimate political homophily

LLMs generate structurally realistic social networks but overestimate political homophily

29 Aug 2024arXiv:2408.16629archive 2025-07-28

Serina Chang, Alicja Chaszczewicz, Emma Wang, Maya Josifovska, Emma Pierson, Jure Leskovec

Generating social networks is essential for many applications, such as epidemic modeling and social simulations. The emergence of generative AI, especially large language models (LLMs), offers new possibilities for social network generation: LLMs can generate networks without additional training or need to define network parameters, and users can flexibly define individuals in the network using natural language. However, this potential raises two critical questions: 1) are the social networks generated by LLMs realistic, and 2) what are risks of bias, given the importance of demographics in forming social ties? To answer these questions, we develop three prompting methods for network generation and compare the generated networks to a suite of real social networks. We find that more realistic networks are generated with "local" methods, where the LLM constructs relations for one persona at a time, compared to "global" methods that construct the entire network at once. We also find that the generated networks match real networks on many characteristics, including density, clustering, connectivity, and degree distribution. However, we find that LLMs emphasize political homophily over all other types of homophily and significantly overestimate political homophily compared to real social networks.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 15 ran (7 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

snap-stanford/llm-social-network officialmentioned in papermentioned on GitHubSyntology: 17 samples, 15 ran (8 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran · our draft was wrong
7ran
2unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from snap-stanford/llm-social-network. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

snap-stanford/llm-social-network official repository 17 samples, 15 ran (8 instrument-failed) · 2 unverified
basic_sanitize bias.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 55fb422341b84630 · report fixture: signature in_string:str/0/str · returned str · level recorded 2026-09-24
bayes_compare_language bias.py ran no licence file found · pointer only · 612f39df05963bc5 · report fixture: signature l1:list/1/str, l2:list/1/str, ngram:int/0/int, prior:float/0/float, cv:NoneType/0/? · returned list · level recorded 2026-09-24
convert_persona_to_string generate_personas.py ran no licence file found · pointer only · 172438fdb9a4ea48 · report fixture: signature name:str/0/str, personas:dict/0/?, demo_keys:list/1/str, demos_to_include:str/0/str · returned str · level recorded 2026-09-24
define_color plotting.py ran · our draft was wrong no licence file found · pointer only · df859c62e17451b0 · report fixture: signature save_names:list/1/str · returned dict · level recorded 2026-09-24
extract_gpt_output constants_and_utils.py ran · our draft was wrong no licence file found · pointer only · 562161f6a0035779 · report fixture: signature response:MockResponse/0/? · returned str · level recorded 2026-09-24
get_node_from_string constants_and_utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 13e836662e2f08c4 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
get_persona_format generate_networks.py ran · our draft was wrong no licence file found · pointer only · d497157741bc59d7 · report fixture: signature demos_to_include:list/1/str · returned str · level recorded 2026-09-24
get_short_name in 6 papers plotting.py ran · our draft was wrong no licence file found · pointer only · a6a19ebad08cbb4e · report fixture: signature save_name:str/0/str, include_model:bool/0/bool · returned str · level recorded 2026-09-24
get_system_prompt in 15 papers generate_networks.py ran no licence file found · pointer only · 0d15a8a4a2812268 · report fixture: signature method:str/0/str, personas:dict/0/?, demos_to_include:list/1/str, curr_pid:NoneType/0/?, G:NoneType/0/?, only_degree:bool/0/bool, num_choices:NoneType/0/?, include_reason:bool/0/bool, all_demos:bool/0/bool · returned str · level recorded 2026-09-24
load_personas_as_dict generate_personas.py ran no licence file found · pointer only · 7fd03899cd7eed64 · report fixture: signature fn:str/0/str, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
make_graph_from_net_file network_datasets.py ran no licence file found · pointer only · 0626acbc6915d7ac · report fixture: signature input:list/1/str, key:str/0/str, directed:bool/0/bool, min_val:int/0/int, max_val:float/0/float, color:NoneType/0/? · returned DiGraph · level recorded 2026-09-24
make_graphs_from_dynetml_file network_datasets.py ran no licence file found · pointer only · 6cfeb489d8339a70 · report fixture: signature fn:str/0/str, min_val:int/0/int, max_val:float/0/float · returned dict · level recorded 2026-09-24
make_graphs_from_paj_file network_datasets.py ran no licence file found · pointer only · 60adc15c14c0c266 · report fixture: signature fn:str/0/str, directed:bool/0/bool, min_val:int/0/int, max_val:float/0/float, color:NoneType/0/? · returned dict · level recorded 2026-09-24
parse_save_name plotting.py ran · our draft was wrong no licence file found · pointer only · de721215ae5496df · report fixture: signature save_name:str/0/str · returned tuple · level recorded 2026-09-24
prop_nodes_in_giant_component constants_and_utils.py ran · our draft was wrong no licence file found · pointer only · db6f594f7abd00c6 · report fixture: signature G:DiGraph/0/? · returned float · level recorded 2026-09-24
get_user_prompt in 5 papers generate_networks.py unverified no licence file found · pointer only · 0d02210460fd59f5 · report
us_population generate_personas.py unverified no licence file found · pointer only · 51f8be307f590f08 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections